Skip to content
Branch: master
Find file History
vkhalidov and facebook-github-bot added GPSm evaluation mode
Summary:
Added evaluation based on GPSm metric, which uses geometric mean of geodesic distance (GPS) and mask intersection over union (IOU) as a proximity measure. As compared to the previous GPS metric, it favors good mask estimates and penalizes situations where all pixels are estimated as foreground.

Created separate files for different test types (following general detectron2 structure). This way it's more convenient to run selected tests.

Reviewed By: MarcSzafraniec

Differential Revision: D19375107

fbshipit-source-id: bec54a897a09b9e43f3332a2e4ada19417b9ef08
Latest commit bcd919d Jan 16, 2020
Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
configs added GPSm evaluation mode Jan 15, 2020
densepose added GPSm evaluation mode Jan 15, 2020
dev adjust model zoo links Oct 18, 2019
doc avoid modifying the inputs in ImageList.from_tensors Jan 7, 2020
README.md add DensePose model zoo Oct 18, 2019
apply_net.py add model arguments to densepose apply_net.py (#650) Jan 9, 2020
query_db.py Initial commit Oct 10, 2019
train_net.py Initial commit Oct 10, 2019

README.md

DensePose in Detectron2

Dense Human Pose Estimation In The Wild

Rıza Alp Güler, Natalia Neverova, Iasonas Kokkinos

[densepose.org] [arXiv] [BibTeX]

Dense human pose estimation aims at mapping all human pixels of an RGB image to the 3D surface of the human body.

In this repository, we provide the code to train and evaluate DensePose-RCNN. We also provide tools to visualize DensePose annotation and results.

Quick Start

See Getting Started

Model Zoo and Baselines

We provide a number of baseline results and trained models available for download. See Model Zoo for details.

License

Detectron2 is released under the Apache 2.0 license

Citing DensePose

If you use DensePose, please use the following BibTeX entry.

@InProceedings{Guler2018DensePose,
  title={DensePose: Dense Human Pose Estimation In The Wild},
  author={R\{i}za Alp G\"uler, Natalia Neverova, Iasonas Kokkinos},
  journal={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2018}
}
You can’t perform that action at this time.